What you have to supply
Capability tells you what a model produces. This tells you what it wants first, which is the part that decides whether you can use it today. 4 require a starting image and 3 require a video file; anything not on that list runs from a text prompt alone.
| Model | You must supply | It will also take |
|---|---|---|
| Bria Video Background Removal | A starting image | — |
| ByteDance Upscaler Video | A starting image | — |
| Sam 3 Video Segment | A text prompt only | — |
| Lucy Restyle | A text prompt only | — |
| Pixverse Effects | A starting image | — |
| Pixverse Transition | A starting image | — |
| LTX 2.3 Retake Video | A text prompt only | — |
| Wan 2.7 Video Edit | A video file | — |
| LTX 2 Retake Video | A text prompt only | — |
| Gemini Omni Flash Edit | A video file | — |
| Happy Horse 1.0 Video Edit | A video file | — |
Read straight off each model's own record — requires_image, requires_video_input, accepts_video_input, max_reference and the per-mode reference configuration. Nothing is inferred from a model's name or description.
All 11 models
Cheapest complete job first. Every row links to that model's spec page — tier and mode variants share a page with the model they are a variant of, so this is products rather than SKUs.
| Model | Provider | Credits per job | Capabilities |
|---|---|---|---|
| Bria Video Background Removal | Bria | 2 credits | this only |
| ByteDance Upscaler Video | ByteDance | 4-346 credits | this only |
| Sam 3 Video Segment | Sam | 4-90 credits | this only |
| Lucy Restyle | Decart | 5-120 credits | this only |
| Pixverse Effects | Pixverse | 15-80 credits | this only |
| Pixverse Transition | Pixverse | 15-80 credits | this only |
| LTX 2.3 Retake Video | LTX | 20-200 credits | this only |
| Wan 2.7 Video Edit | Wan | 24-180 credits | this only |
| LTX 2 Retake Video | LTX | 30-100 credits | this only |
| Gemini Omni Flash Edit | 63-1500 credits | this only | |
| Happy Horse 1.0 Video Edit | Alibaba | 70-3360 credits | this only |
How these models are billed
Four different billing shapes across the roster, which is why a straight comparison of headline figures between two of these models can mislead.
- Charged per second of output5 models
- Charged per second, at a rate that changes with output resolution3 models
- Charged by output resolution, audio and clip length2 models
- Charged a flat rate per generation1 model
All figures are Versely credits. A credit figure marked as a headline rate is not the cost of a complete job. Your plan's credit allowance is on the pricing page.
More capability pages
Every model on Versely · Model providers · Ranked buyer guides
Frequently asked questions
How many edit video models does Versely have?+
11 with a spec page — all of them video models, from 9 providers. Tier and mode variants of the same model share a page with the model they are a variant of, so this is products rather than SKUs.
What do edit video models need as input?+
4 of the 11 require a starting image, 3 require a video file, 0 accept a video without requiring one and 0 take reference images. Anything not on that list runs from a text prompt alone, and every figure here is read off the model's own record rather than inferred from its name.
What does an edit video job cost?+
Complete jobs run 2 to 70 credits across the 11.
Run every one of them on one subscription
The all-in-one AI studio for creators. 60+ models for video, image, voice, music and lipsync in a single app.